library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(sf)
## Linking to GEOS 3.9.1, GDAL 3.3.2, PROJ 7.2.1; sf_use_s2() is TRUE
library(leaflet)
## Warning: package 'leaflet' was built under R version 4.2.1
library(DT)
library(readr)
library(ggplot2)
library(plotly)
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✔ tibble 3.1.7 ✔ stringr 1.4.0
## ✔ tidyr 1.2.0 ✔ forcats 0.5.1
## ✔ purrr 0.3.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ plotly::filter() masks dplyr::filter(), stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library(terra)
## Warning: package 'terra' was built under R version 4.2.1
## terra 1.5.34
##
## Attaching package: 'terra'
## The following object is masked from 'package:tidyr':
##
## extract
library(sf)
library(stringi)
library(readxl)
cantones <-
st_read(dsn = "C:/Users/Bryan/OneDrive/Desktop/Procesamiento de Datos/Tarea3/cantones_simplificados.geojson", quiet = TRUE) %>%
st_transform(4326)
# Transformación de datos de cantones
estadisticas_policiales <-
readxl::read_excel (
"C:/Users/Bryan/OneDrive/Desktop/Procesamiento de Datos/Tarea3/estadisticaspoliciales2021.xls"
)
Mapa de cantones
# Lectura
cantones <-
st_read(dsn = "C:/Users/Bryan/OneDrive/Desktop/Procesamiento de Datos/Tarea3/cantones_simplificados.geojson",
quiet = TRUE) %>%
st_transform(4326) # transformación a WGS84
# Transformación
cantones <-
cantones %>%
st_transform(5367) %>%
st_simplify(dTolerance = 100) %>% # simplificación de geometrías
st_transform(4326)
# En el data frame de cantones
cantones <-
cantones %>%
mutate(canton_normalizado = tolower(stri_trans_general(canton, id = "Latin-ASCII")))
delitos <-
read_xls(path = "C:/Users/Bryan/OneDrive/Desktop/Procesamiento de Datos/Tarea3/estadisticaspoliciales2021.xls")
delitos <-
delitos %>%
mutate(canton_normalizado = tolower(stri_trans_general(Canton, id = "Latin-ASCII")))
delitos %>%
left_join(
dplyr::select(st_drop_geometry(cantones),
canton_normalizado, cod_canton),
by = "canton_normalizado",
copy = FALSE,
keep = FALSE
) %>%
filter(is.na(cod_canton) &
canton_normalizado != "desconocido") %>% # los cod_canton = NA son los que no están en el data frame de cantones
distinct(canton_normalizado)
## # A tibble: 2 × 1
## canton_normalizado
## <chr>
## 1 leon cortes
## 2 vasquez de coronado
delitos <-
delitos %>%
mutate(Canton = if_else(Canton == "LEON CORTES", "LEON CORTES CASTRO", Canton)) %>%
mutate(Canton = if_else(Canton == "VASQUEZ DE CORONADO", "VAZQUEZ DE CORONADO", Canton))
delitos <-
delitos %>%
mutate(canton_normalizado = tolower(stri_trans_general(Canton, id = "Latin-ASCII")))
delitos %>%
left_join(
dplyr::select(st_drop_geometry(cantones),
canton_normalizado, cod_canton),
by = "canton_normalizado",
copy = FALSE,
keep = FALSE
) %>%
filter(is.na(cod_canton) &
canton_normalizado != "desconocido") %>%
distinct(canton_normalizado)
## # A tibble: 0 × 1
## # … with 1 variable: canton_normalizado <chr>
delitos <-
delitos %>%
left_join(
dplyr::select(st_drop_geometry(cantones),
cod_canton,
canton_normalizado),
by = "canton_normalizado",
copy = FALSE,
keep = FALSE
)
delitos_x_canton <-
delitos %>%
count(cod_canton, name = "delitos")
cantones_delitos <-
cantones %>%
left_join(delitos_x_canton,
by = "cod_canton",
copy = FALSE,
keep = FALSE)
colores_cantones_delitos <-
colorNumeric(palette = "Blues",
domain = cantones_delitos$delitos,
na.color = "transparent")
leaflet() %>%
setView(
lng = -84.19452,
lat = 9.572735,
zoom = 7) %>%
addTiles(group = "OpenStreetMap") %>% # capa base
addPolygons(
data = cantones_delitos,
fillColor = ~ colores_cantones_delitos(cantones_delitos$delitos),
fillOpacity = 0.8,
color = "black",
stroke = TRUE,
weight = 1.0,
popup = paste(
paste("<strong>Cantón:</strong>",
cantones_delitos$canton),
paste("<strong>Delitos:</strong>",
cantones_delitos$delitos),
sep = '<br/>'
),
group = "Delitos en cantones"
) %>%
addLayersControl(
baseGroups = c("OpenStreetMap"),
overlayGroups = c("Delitos en cantones")
) %>%
addLegend(
position = "bottomleft",
pal = colores_cantones_delitos,
values = cantones_delitos$delitos,
group = "Delitos",
title = "Cantidad de delitos"
)
Tabla
estadisticas_policiales <-
readxl::read_excel (
"C:/Users/Bryan/OneDrive/Desktop/Procesamiento de Datos/Tarea3/estadisticaspoliciales2021.xls"
)
estadisticas_policiales <-
estadisticas_policiales %>%
select(Delito = Delito,
Fecha,
Victima,
Edad,
Genero = Genero,
Provincia,
Canton) %>%
mutate(Fecha = as.Date(Fecha, format = "%d/%m/%Y"))
estadisticas_policiales %>%
datatable(
colnames = c(
"Delito",
"Fecha",
"Victima",
"Edad",
"Genero",
"Provincia",
"Canton"
),
options = list(
pageLength = 5,
language = list(url = '//cdn.datatables.net/plug-ins/1.10.11/i18n/Spanish.json')
)
)
## Warning in instance$preRenderHook(instance): It seems your data is too big
## for client-side DataTables. You may consider server-side processing: https://
## rstudio.github.io/DT/server.html
Grafico de Delitos
ggplot2_barras_proporcion <-
estadisticas_policiales %>%
ggplot(aes(
x = Delito,
y = stat(count),
group = 100
)) +
geom_bar() +
ggtitle("Tipos de Delitos") +
xlab("Delito") +
ylab("Cantidad") +
theme_minimal()
ggplotly(ggplot2_barras_proporcion) %>% config(locale = 'es')
Grafico por victima
delitos_tipo <-
delitos %>%
count(Victima) %>%
ggplot(aes(x = reorder(Victima, n), y = n)) +
geom_bar(stat = "identity") +
ggtitle("Delitos por tipo") +
xlab("Tipo de delito") +
ylab("Victimas") +
coord_flip()
delitos_tipo %>%
ggplotly() %>%
config(locale = 'es')
Grafico por mes
ggplot2_histograma_estadisticas_policiales <-
estadisticas_policiales %>%
ggplot(aes(x = Fecha)) +
geom_histogram(binwidth = 80) +
ggtitle("Delitos por Mes") +
xlab("Fecha") +
ylab("Cantidad de Delitos") +
theme_minimal()
ggplotly(ggplot2_histograma_estadisticas_policiales) %>% config(locale = 'es')
Grafico barras apiladas
ggplot2_barras_apiladas_cantidad <-
estadisticas_policiales %>%
ggplot(aes(x = Delito, fill = Genero)) +
geom_bar(position = "fill") +
ggtitle("Proporcion de delito por genero") +
xlab("Delito") +
ylab("Cantidad") +
labs(fill = "Delito") +
theme_minimal()
ggplotly(ggplot2_barras_apiladas_cantidad) %>% config(locale = 'es')